DELCODE_Analysis_Olink only
1. Load all libraries required
library(readxl)
library(tidyverse)Registered S3 methods overwritten by 'dbplyr':
method from
print.tbl_lazy
print.tbl_sql ── Attaching packages ─────────────────────────────────────────────────────── tidyverse 1.3.2 ──
✔ ggplot2 3.4.0 ✔ purrr 0.3.4
✔ tibble 3.1.7 ✔ dplyr 1.0.9
✔ tidyr 1.2.0 ✔ stringr 1.4.0
✔ readr 2.1.3 ✔ forcats 0.5.2
── Conflicts ────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()library('dplyr')
library('readxl')
library(ggplot2)
library(dplyr) # required by custom function outlier_removal()
library(jmv) # ancova()
library(ggplot2) # ggplot()
library(gridExtra) # grid.arrange()
Attaching package: ‘gridExtra’
The following object is masked from ‘package:dplyr’:
combineolink_delcode<- read_excel('DELCODE_olinkonly.xlsx')
olink_delcode <- data.frame(olink_delcode)2. Pre analysis: Data import and cleaning
colnames(olink_delcode) [1] "Repseudonym" "Barcode_CSF" "sex" "Age" "prmdiag"
[6] "bmi" "ApoE" "E4_Positive" "AB_Ratio_Patho" "tTau_Patho"
[11] "AT" "AN" "YKL40_NPX" "AXL_NPX" "TYRO3_NPX"
[16] "TREM2_NPX" "MIF_NPX" "TNFR1_NPX" "TNFR2_NPX" "C1q_NPX"
[21] "C3_NPX" "Factor_B_NPX" "Factor_H_NPX" "ICAM1_NPX" "VCAM1_NPX" DC_thesis_olink <- subset(olink_delcode, select = c(Barcode_CSF,
YKL40_NPX, AXL_NPX, TYRO3_NPX,
TREM2_NPX, C1q_NPX, C3_NPX,
Factor_B_NPX, Factor_H_NPX, MIF_NPX,
TNFR1_NPX, TNFR2_NPX, ICAM1_NPX, VCAM1_NPX,
Age, sex, bmi, E4_Positive,
prmdiag, AB_Ratio_Patho, tTau_Patho, AT, AN))
DC_thesis_olink$A_N_cat <- factor(ifelse(DC_thesis_olink$AN == 0,
"A-T-",
ifelse(DC_thesis_olink$AN == 2,
"A+T-",
ifelse(DC_thesis_olink$AN == 1,
"A-T+",
"A+T+"))),
levels = c("A-T-", "A-T+", "A+T-", "A+T+"))
table(DC_thesis_olink$A_N_cat)
A-T- A-T+ A+T- A+T+
245 24 92 120 DC_thesis_olink$Diag <- factor(ifelse(DC_thesis_olink$prmdiag == 0 | DC_thesis_olink$prmdiag == 100,
"CN",
ifelse(DC_thesis_olink$prmdiag == 1,
"SCD",
ifelse(DC_thesis_olink$prmdiag == 2,
"MCI", "DAT"))),
levels = c('CN',"SCD", "MCI", "DAT"))
table(DC_thesis_olink$Diag)
CN SCD MCI DAT
126 194 104 60 DC_thesis_olink$clinical_N_cat <- factor(ifelse(DC_thesis_olink$Diag == "CN" &
DC_thesis_olink$tTau_Patho == 0,
"CN_T-",
ifelse(DC_thesis_olink$Diag == "CN" &
DC_thesis_olink$tTau_Patho == 1,
"CN_T+",
ifelse(DC_thesis_olink$Diag == "SCD" &
DC_thesis_olink$tTau_Patho == 0,
"SCD_T-",
ifelse(DC_thesis_olink$Diag == "SCD" &
DC_thesis_olink$tTau_Patho == 1,
"SCD_T+",
ifelse(DC_thesis_olink$Diag == "MCI" &
DC_thesis_olink$tTau_Patho == 0,
"MCI_T-",
ifelse(DC_thesis_olink$Diag == "MCI" &
DC_thesis_olink$tTau_Patho == 1,
"MCI_T+",
ifelse(DC_thesis_olink$Diag == "DAT" &
DC_thesis_olink$tTau_Patho == 0,
"DAT_T-",
ifelse(DC_thesis_olink$Diag == "DAT" &
DC_thesis_olink$tTau_Patho == 1,
"DAT_T+", 'others')))))))),
levels = c('CN_T-',"CN_T+", 'SCD_T-', 'SCD_T+', "MCI_T-", "MCI_T+","DAT_T-", "DAT_T+"))
table(DC_thesis_olink$clinical_N_cat)
CN_T- CN_T+ SCD_T- SCD_T+ MCI_T- MCI_T+ DAT_T- DAT_T+
104 22 160 34 56 46 17 42 Outlier removal function Higher than or less than 3 standard deviations
outlier_removal <- function(df) {
find.outlier <- function(df) {
if(!is.numeric(df)) {
df
}
else {
arith.mean <- mean(df, na.rm = TRUE)
st.dev <- sd(df, na.rm = TRUE)
df[which(df > (arith.mean + 3*st.dev) | df < (arith.mean - 3*st.dev))] <- NA
df
}
}
df %>% dplyr::mutate_all(find.outlier)
}Removed outliers
DC_thesis_olink_clean <- outlier_removal(DC_thesis_olink[1:14])
dim(DC_thesis_olink_clean)[1] 484 14Check for merge outlier removed columns
DC_thesis_o <- merge(DC_thesis_olink_clean,
DC_thesis_olink[c(1, 15:ncol(DC_thesis_olink))],
by = "Barcode_CSF")
dim(DC_thesis_o)[1] 484 26DC_thesis_o <- na.omit(DC_thesis_o)table(DC_thesis_o$A_N_cat)
A-T- A-T+ A+T- A+T+
216 21 83 106 table(DC_thesis_o$Diag)
CN SCD MCI DAT
109 175 90 52 table(DC_thesis_o$clinical_N_cat)
CN_T- CN_T+ SCD_T- SCD_T+ MCI_T- MCI_T+ DAT_T- DAT_T+
90 19 145 30 47 43 17 35 Making BMI as character
DC_thesis_o$bmi <- as.numeric(as.character(DC_thesis_o$bmi)) colnames(DC_thesis_o)
[1] "Barcode_CSF" "YKL40_NPX" "AXL_NPX" "TYRO3_NPX" "TREM2_NPX"
[6] "C1q_NPX" "C3_NPX" "Factor_B_NPX" "Factor_H_NPX" "MIF_NPX"
[11] "TNFR1_NPX" "TNFR2_NPX" "ICAM1_NPX" "VCAM1_NPX" "Age"
[16] "sex" "bmi" "E4_Positive" "prmdiag" "AB_Ratio_Patho"
[21] "tTau_Patho" "AT" "AN" "A_N_cat" "Diag"
[26] "clinical_N_cat"3. AT scheme
3.1. YKL40_AT
(YKL40_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = YKL40_NPX ,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "YKL40 (NPX)") +
scale_y_continuous(breaks = seq(3,9, by = 1), limits = c(3,9)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = YKL40_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = YKL40_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - YKL40_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
A_N_cat 11.7657273 3 3.9219091 22.7350558 < .0000001
Age 9.6214161 1 9.6214161 55.7747324 < .0000001
sex 0.7964757 1 0.7964757 4.6171187 0.0322281
bmi 0.1154201 1 0.1154201 0.6690828 0.4138376
E4_Positive 0.1376713 1 0.1376713 0.7980718 0.3721845
Residuals 72.1070588 418 0.1725049
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.43620545 0.09600570 418.0000 -4.5435371 0.0000435
- A+T- -0.04072629 0.06026469 418.0000 -0.6757902 1.0000000
- A+T+ -0.38765966 0.05658273 418.0000 -6.8512011 < .0000001
A-T+ - A+T- 0.39547916 0.10565811 418.0000 3.7430079 0.0012436
- A+T+ 0.04854579 0.10323609 418.0000 0.4702405 1.0000000
A+T- - A+T+ -0.34693337 0.06113807 418.0000 -5.6745885 0.0000002
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(YKL40_NPX, na.rm = TRUE), Std=sd(YKL40_NPX, na.rm = TRUE),
Max=max(YKL40_NPX, na.rm = TRUE), Min=min(YKL40_NPX, na.rm = TRUE))NA3.2. Axl_AT
(AXL_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = AXL_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "AXL (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = AXL_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = AXL_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - AXL_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
A_N_cat 8.923849093 3 2.974616364 19.41113827 < .0000001
Age 0.851292019 1 0.851292019 5.55518597 0.0188864
sex 1.270724020 1 1.270724020 8.29222886 0.0041862
bmi 0.269418000 1 0.269418000 1.75811245 0.1855842
E4_Positive 0.006962198 1 0.006962198 0.04543248 0.8313147
Residuals 64.055472830 418 0.153242758
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.4904526 0.09048701 418.0000 -5.420144 0.0000006
- A+T- 0.1074292 0.05680050 418.0000 1.891342 0.3556187
- A+T+ -0.2031011 0.05333019 418.0000 -3.808369 0.0009651
A-T+ - A+T- 0.5978818 0.09958458 418.0000 6.003759 < .0000001
- A+T+ 0.2873515 0.09730178 418.0000 2.953199 0.0199348
A+T- - A+T+ -0.3105302 0.05762367 418.0000 -5.388935 0.0000007
─────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(AXL_NPX, na.rm = TRUE), Std=sd(AXL_NPX, na.rm = TRUE),
Max=max(AXL_NPX, na.rm = TRUE), Min=min(AXL_NPX, na.rm = TRUE))3.3. Tyro3_AT
(Tyro3_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = TYRO3_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Tyro3 (NPX)") +
scale_y_continuous(breaks = seq(2, 6, by = 1), limits = c(2,6)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TYRO3_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TYRO3_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TYRO3_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
A_N_cat 4.888160573 3 1.629386858 18.50020664 < .0000001
Age 0.632224385 1 0.632224385 7.17833319 0.0076702
sex 0.154161880 1 0.154161880 1.75036801 0.1865537
bmi 0.413577360 1 0.413577360 4.69579497 0.0308007
E4_Positive 0.005425516 1 0.005425516 0.06160180 0.8041038
Residuals 36.814924274 418 0.088073982
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.3365132 0.06859936 418.0000 -4.905485 0.0000080
- A+T- 0.1216140 0.04306119 418.0000 2.824214 0.0297988
- A+T+ -0.1238764 0.04043030 418.0000 -3.063949 0.0139546
A-T+ - A+T- 0.4581272 0.07549634 418.0000 6.068204 < .0000001
- A+T+ 0.2126368 0.07376573 418.0000 2.882596 0.0248858
A+T- - A+T+ -0.2454904 0.04368524 418.0000 -5.619527 0.0000002
─────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(TYRO3_NPX, na.rm = TRUE), Std=sd(TYRO3_NPX, na.rm = TRUE),
Max=max(TYRO3_NPX, na.rm = TRUE), Min=min(TYRO3_NPX, na.rm = TRUE))3.4. TREM2_AT
(TREM2_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = TREM2_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TREM2 (NPX)") +
scale_y_continuous(breaks = seq(0, 8, by = 1), limits = c(0,8)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TREM2_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TREM2_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TREM2_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
A_N_cat 21.5227024 3 7.1742341 14.4479563 < .0000001
Age 6.2170928 1 6.2170928 12.5204005 0.0004477
sex 1.1990359 1 1.1990359 2.4146993 0.1209578
bmi 1.1558506 1 1.1558506 2.3277298 0.1278434
E4_Positive 0.2982253 1 0.2982253 0.6005863 0.4387926
Residuals 207.5608342 418 0.4965570
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.80205967 0.16288490 418.0000 -4.9240886 0.0000073
- A+T- -0.04748003 0.10224610 418.0000 -0.4643701 1.0000000
- A+T+ -0.43690772 0.09599922 418.0000 -4.5511590 0.0000420
A-T+ - A+T- 0.75457964 0.17926135 418.0000 4.2093827 0.0001882
- A+T+ 0.36515195 0.17515211 418.0000 2.0847704 0.2261792
A+T- - A+T+ -0.38942769 0.10372788 418.0000 -3.7543202 0.0011905
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(TREM2_NPX, na.rm = TRUE), Std=sd(TREM2_NPX, na.rm = TRUE),
Max=max(TREM2_NPX, na.rm = TRUE), Min=min(TREM2_NPX, na.rm = TRUE))3.5. C1q_AT
(C1q_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = C1q_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "C1q (NPX)") +
scale_y_continuous(breaks = seq(-4, 1, by = 1), limits = c(-4,1)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = C1q_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = C1q_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - C1q_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
A_N_cat 4.93452704 3 1.64484235 10.9742979 0.0000006
Age 4.45758032 1 4.45758032 29.7407313 < .0000001
sex 0.93314380 1 0.93314380 6.2258842 0.0129744
bmi 0.03047065 1 0.03047065 0.2032985 0.6523053
E4_Positive 0.05610176 1 0.05610176 0.3743079 0.5409980
Residuals 62.65039535 418 0.14988133
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.28632829 0.08948908 418.0000 -3.1995893 0.0088867
- A+T- 0.06919775 0.05617408 418.0000 1.2318448 1.0000000
- A+T+ -0.19554760 0.05274204 418.0000 -3.7076230 0.0014244
A-T+ - A+T- 0.35552604 0.09848631 418.0000 3.6099030 0.0020608
- A+T+ 0.09078069 0.09622869 418.0000 0.9433849 1.0000000
A+T- - A+T+ -0.26474534 0.05698817 418.0000 -4.6456192 0.0000273
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(C1q_NPX, na.rm = TRUE), Std=sd(C1q_NPX, na.rm = TRUE),
Max=max(C1q_NPX, na.rm = TRUE), Min=min(C1q_NPX, na.rm = TRUE))NA3.6. C3_AT
(C3_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = C3_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "C3 (NPX)") +
scale_y_continuous(breaks = seq(-2.5, 5, by = 2.5), limits = c(-2.5,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = C3_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = C3_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - C3_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
A_N_cat 0.167368201 3 0.055789400 0.163446711 0.9209433
Age 2.045097430 1 2.045097430 5.991540474 0.0147851
sex 3.938390743 1 3.938390743 11.538339049 0.0007470
bmi 4.373970735 1 4.373970735 12.814461701 0.0003843
E4_Positive 0.001251925 1 0.001251925 0.003667777 0.9517368
Residuals 142.676283252 418 0.341330821
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
───────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
───────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ 0.001386141 0.13504671 418.0000 0.01026416 1.0000000
- A+T- -0.025252431 0.08477152 418.0000 -0.29788816 1.0000000
- A+T+ -0.054856098 0.07959227 418.0000 -0.68921387 1.0000000
A-T+ - A+T- -0.026638571 0.14862431 418.0000 -0.17923428 1.0000000
- A+T+ -0.056242238 0.14521737 418.0000 -0.38729690 1.0000000
A+T- - A+T+ -0.029603667 0.08600005 418.0000 -0.34422848 1.0000000
───────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(C3_NPX, na.rm = TRUE), Std=sd(C3_NPX, na.rm = TRUE),
Max=max(C3_NPX, na.rm = TRUE), Min=min(C3_NPX, na.rm = TRUE))NA3.7. FB_AT
(FB_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = Factor_B_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Factor B (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = Factor_B_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = Factor_B_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - Factor_B_NPX
──────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
──────────────────────────────────────────────────────────────────────────────────
A_N_cat 0.89061401 3 0.29687134 1.1923865 0.3122780
Age 0.15970641 1 0.15970641 0.6414623 0.4236368
sex 1.34262338 1 1.34262338 5.3926594 0.0207012
bmi 5.33243228 1 5.33243228 21.4177641 0.0000049
E4_Positive 0.05666330 1 0.05666330 0.2275887 0.6335669
Residuals 104.07046596 418 0.24897241
──────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.13038576 0.11533785 418.0000 -1.1304680 1.0000000
- A+T- 0.02128949 0.07239987 418.0000 0.2940543 1.0000000
- A+T+ -0.08567307 0.06797649 418.0000 -1.2603338 1.0000000
A-T+ - A+T- 0.15167525 0.12693393 418.0000 1.1949150 1.0000000
- A+T+ 0.04471269 0.12402420 418.0000 0.3605158 1.0000000
A+T- - A+T+ -0.10696256 0.07344911 418.0000 -1.4562812 0.8763936
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(Factor_B_NPX, na.rm = TRUE), Std=sd(Factor_B_NPX, na.rm = TRUE),
Max=max(Factor_B_NPX, na.rm = TRUE), Min=min(Factor_B_NPX, na.rm = TRUE))3.8. FH_AT
(FH_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = Factor_H_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Factor H (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = Factor_H_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = Factor_H_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - Factor_H_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
A_N_cat 4.262885291 3 1.420961764 8.70858973 0.0000129
Age 1.807445844 1 1.807445844 11.07721876 0.0009513
sex 4.647819852 1 4.647819852 28.48490175 0.0000002
bmi 2.073885349 1 2.073885349 12.71013557 0.0004057
E4_Positive 0.004690762 1 0.004690762 0.02874808 0.8654440
Residuals 68.204156552 418 0.163167839
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.30570286 0.09337133 418.0000 -3.2740550 0.0068900
- A+T- 0.04971858 0.05861105 418.0000 0.8482800 1.0000000
- A+T+ -0.17698295 0.05503012 418.0000 -3.2161108 0.0084024
A-T+ - A+T- 0.35542144 0.10275889 418.0000 3.4587904 0.0035900
- A+T+ 0.12871991 0.10040333 418.0000 1.2820284 1.0000000
A+T- - A+T+ -0.22670153 0.05946046 418.0000 -3.8126437 0.0009491
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(Factor_H_NPX, na.rm = TRUE), Std=sd(Factor_H_NPX, na.rm = TRUE),
Max=max(Factor_H_NPX, na.rm = TRUE), Min=min(Factor_H_NPX, na.rm = TRUE))3.9. MIF_AT
(MIF_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = MIF_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "MIF (NPX)") +
scale_y_continuous(breaks = seq(2, 8, by = 2), limits = c(2,8)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = MIF_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = MIF_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - MIF_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
A_N_cat 21.77732616 3 7.25910872 38.3812560 < .0000001
Age 5.16885551 1 5.16885551 27.3294111 0.0000003
sex 0.68806346 1 0.68806346 3.6380141 0.0571594
bmi 0.15906397 1 0.15906397 0.8410226 0.3596333
E4_Positive 0.03179824 1 0.03179824 0.1681276 0.6819914
Residuals 79.05701278 418 0.18913161
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.67111201 0.10052598 418.0000 -6.6760056 < .0000001
- A+T- 0.04803969 0.06310216 418.0000 0.7613001 1.0000000
- A+T+ -0.45012196 0.05924684 418.0000 -7.5974001 < .0000001
A-T+ - A+T- 0.71915169 0.11063287 418.0000 6.5003440 < .0000001
- A+T+ 0.22099004 0.10809681 418.0000 2.0443716 0.2492573
A+T- - A+T+ -0.49816165 0.06401666 418.0000 -7.7817501 < .0000001
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(MIF_NPX, na.rm = TRUE), Std=sd(MIF_NPX, na.rm = TRUE),
Max=max(MIF_NPX, na.rm = TRUE), Min=min(MIF_NPX, na.rm = TRUE))3.10. TNFR1_AT
(TNFR1_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = TNFR1_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TNFR1 (NPX)") +
scale_y_continuous(breaks = seq(0, 6, by = 2), limits = c(0,6)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TNFR1_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TNFR1_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TNFR1_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
A_N_cat 8.743021879 3 2.914340626 24.69981960 < .0000001
Age 2.705371062 1 2.705371062 22.92874641 0.0000023
sex 0.832566269 1 0.832566269 7.05622276 0.0082013
bmi 6.008044e-5 1 6.008044e-5 5.091979e-4 0.9820077
E4_Positive 0.003507677 1 0.003507677 0.02972850 0.8631911
Residuals 49.319970826 418 0.117990361
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.44272830 0.07939982 418.0000 -5.575936 0.0000003
- A+T- 0.06695827 0.04984085 418.0000 1.343441 1.0000000
- A+T+ -0.25433816 0.04679575 418.0000 -5.435070 0.0000006
A-T+ - A+T- 0.50968656 0.08738268 418.0000 5.832810 < .0000001
- A+T+ 0.18839013 0.08537959 418.0000 2.206501 0.1673522
A+T- - A+T+ -0.32129643 0.05056316 418.0000 -6.354358 < .0000001
─────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(TNFR1_NPX, na.rm = TRUE), Std=sd(TNFR1_NPX, na.rm = TRUE),
Max=max(TNFR1_NPX, na.rm = TRUE), Min=min(TNFR1_NPX, na.rm = TRUE))3.11. TNFR2_AT
(TNFR2_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = TNFR2_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TNFR2 (NPX)") +
scale_y_continuous(breaks = seq(-1, 4, by = 1), limits = c(-1,4)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TNFR2_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TNFR2_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TNFR2_NPX
─────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
─────────────────────────────────────────────────────────────────────────────────────
A_N_cat 10.898921737 3 3.632973912 27.010709836 < .0000001
Age 5.946841316 1 5.946841316 44.214026610 < .0000001
sex 1.905597715 1 1.905597715 14.167882347 0.0001911
bmi 0.001292876 1 0.001292876 0.009612370 0.9219454
E4_Positive 0.065730088 1 0.065730088 0.488695042 0.4848988
Residuals 56.221517483 418 0.134501238
─────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.42424357 0.08477336 418.0000 -5.0044444 0.0000050
- A+T- 0.03067686 0.05321393 418.0000 0.5764818 1.0000000
- A+T+ -0.33780280 0.04996274 418.0000 -6.7610938 < .0000001
A-T+ - A+T- 0.45492043 0.09329648 418.0000 4.8760729 0.0000092
- A+T+ 0.08644077 0.09115783 418.0000 0.9482539 1.0000000
A+T- - A+T+ -0.36847966 0.05398512 418.0000 -6.8255780 < .0000001
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(TNFR2_NPX, na.rm = TRUE), Std=sd(TNFR2_NPX, na.rm = TRUE),
Max=max(TNFR2_NPX, na.rm = TRUE), Min=min(TNFR2_NPX, na.rm = TRUE))3.12. ICAM1_AT
(ICAM1_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = ICAM1_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "ICAM1 (NPX)") +
scale_y_continuous(breaks = seq(-6,0, by = 1), limits = c(-6, 0)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = ICAM1_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = ICAM1_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - ICAM1_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
A_N_cat 4.883671641 3 1.627890547 10.60914025 0.0000010
Age 2.101375800 1 2.101375800 13.69489529 0.0002438
sex 1.173366409 1 1.173366409 7.64695687 0.0059387
bmi 0.719026934 1 0.719026934 4.68597695 0.0309751
E4_Positive 0.002154858 1 0.002154858 0.01404345 0.9057244
Residuals 64.138868251 418 0.153442269
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
───────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
───────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.363427430 0.09054589 418.0000 -4.01373724 0.0004250
- A+T- -0.002568053 0.05683747 418.0000 -0.04518239 1.0000000
- A+T+ -0.207678355 0.05336489 418.0000 -3.89166622 0.0006950
A-T+ - A+T- 0.360859377 0.09964938 418.0000 3.62129064 0.0019748
- A+T+ 0.155749075 0.09736510 418.0000 1.59963962 0.6626045
A+T- - A+T+ -0.205110303 0.05766117 418.0000 -3.55716506 0.0025069
───────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(ICAM1_NPX, na.rm = TRUE), Std=sd(ICAM1_NPX, na.rm = TRUE),
Max=max(ICAM1_NPX, na.rm = TRUE), Min=min(ICAM1_NPX, na.rm = TRUE))3.13. VCAM1_AT
(VCAM1_A_T_plot <- ggplot(DC_thesis_o,
aes(x = A_N_cat, y = VCAM1_NPX,
colour = A_N_cat, fill = A_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "VCAM1 (NPX)") +
scale_y_continuous(breaks = seq(-4,1, by = 1), limits = c(-4, 1)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_brewer(palette = "Accent") +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = VCAM1_NPX ~ A_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = VCAM1_NPX ~ A_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - VCAM1_NPX
─────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
─────────────────────────────────────────────────────────────────────────────────────
A_N_cat 5.4728949 3 1.8242983 15.967479463 < .0000001
Age 2.6626682 1 2.6626682 23.305453614 0.0000019
sex 3.2286382 1 3.2286382 28.259201822 0.0000002
bmi 0.1902123 1 0.1902123 1.664865427 0.1976610
E4_Positive 6.676904e-4 1 6.676904e-4 0.005844073 0.9391004
Residuals 47.7568604 418 0.1142509
─────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - A_N_cat
──────────────────────────────────────────────────────────────────────────────────────────────────────
A_N_cat A_N_cat Mean Difference SE df t p-bonferroni
──────────────────────────────────────────────────────────────────────────────────────────────────────
A-T- - A-T+ -0.40049158 0.07813147 418.0000 -5.1258676 0.0000027
- A+T- 0.01534909 0.04904468 418.0000 0.3129613 1.0000000
- A+T+ -0.20139767 0.04604822 418.0000 -4.3736252 0.0000927
A-T+ - A+T- 0.41584066 0.08598681 418.0000 4.8360981 0.0000112
- A+T+ 0.19909390 0.08401572 418.0000 2.3697220 0.1095285
A+T- - A+T+ -0.21674676 0.04975545 418.0000 -4.3562412 0.0001000
──────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(A_N_cat)%>%
summarise(Median=median(VCAM1_NPX, na.rm = TRUE), Std=sd(VCAM1_NPX, na.rm = TRUE),
Max=max(VCAM1_NPX, na.rm = TRUE), Min=min(VCAM1_NPX, na.rm = TRUE))4. Diagnosis scheme
4.1. YKL40_Diag
(YKL40_diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = YKL40_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "YKL40 (NPXL)") +
scale_y_continuous(breaks = seq(3,9, by = 1), limits = c(3,9)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = YKL40_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = YKL40_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - YKL40_NPX
─────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
─────────────────────────────────────────────────────────────────────────────────────
Diag 4.2741905 3 1.4247302 7.481755332 0.0000688
Age 11.5133953 1 11.5133953 60.460855950 < .0000001
sex 1.2660313 1 1.2660313 6.648371904 0.0102658
bmi 0.7231212 1 0.7231212 3.797361769 0.0520021
E4_Positive 7.295689e-4 1 7.295689e-4 0.003831221 0.9506746
Residuals 79.5985955 418 0.1904273
─────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.09721385 0.05492361 418.0000 1.7699830 0.4647534
- MCI -0.12726004 0.06461891 418.0000 -1.9693931 0.2974077
- DAT -0.16721530 0.08101355 418.0000 -2.0640411 0.2377823
SCD - MCI -0.22447389 0.05691828 418.0000 -3.9437926 0.0005642
- DAT -0.26442915 0.07254896 418.0000 -3.6448370 0.0018076
MCI - DAT -0.03995526 0.07828349 418.0000 -0.5103919 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(YKL40_NPX, na.rm = TRUE), Std=sd(YKL40_NPX, na.rm = TRUE),
Max=max(YKL40_NPX, na.rm = TRUE), Min=min(YKL40_NPX, na.rm = TRUE))4.2. Axl_Diag
(AXL_diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = AXL_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "AXL (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = AXL_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = AXL_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - AXL_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
Diag 0.674130199 3 0.224710066 1.29906035 0.2742929
Age 1.762043930 1 1.762043930 10.18646580 0.0015216
sex 1.336263991 1 1.336263991 7.72501026 0.0056919
bmi 0.925955523 1 0.925955523 5.35299609 0.0211710
E4_Positive 0.006857369 1 0.006857369 0.03964280 0.8422774
Residuals 72.305191723 418 0.172978928
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.09306956 0.05234691 418.0000 1.7779379 0.4568457
- MCI 0.04150848 0.06158738 418.0000 0.6739771 1.0000000
- DAT 0.11104174 0.07721287 418.0000 1.4381247 0.9068816
SCD - MCI -0.05156108 0.05424801 418.0000 -0.9504696 1.0000000
- DAT 0.01797218 0.06914539 418.0000 0.2599187 1.0000000
MCI - DAT 0.06953326 0.07461088 418.0000 0.9319453 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(AXL_NPX, na.rm = TRUE), Std=sd(AXL_NPX, na.rm = TRUE),
Max=max(AXL_NPX, na.rm = TRUE), Min=min(AXL_NPX, na.rm = TRUE))4.3. Tyro3_Diag
(Tyro3_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = TYRO3_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Tyro3 (NPX)") +
scale_y_continuous(breaks = seq(2, 6, by = 1), limits = c(2,6)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TYRO3_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TYRO3_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TYRO3_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
Diag 0.823692457 3 0.274564152 2.80747362 0.0393300
Age 1.330128254 1 1.330128254 13.60082863 0.0002559
sex 0.148209341 1 0.148209341 1.51547028 0.2189985
bmi 0.930758134 1 0.930758134 9.51718891 0.0021708
E4_Positive 0.002194833 1 0.002194833 0.02244261 0.8809879
Residuals 40.879392390 418 0.097797589
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.087737540 0.03936031 418.0000 2.2290864 0.1580339
- MCI 0.081875962 0.04630834 418.0000 1.7680610 0.4666807
- DAT 0.156535120 0.05805735 418.0000 2.6962155 0.0437791
SCD - MCI -0.005861578 0.04078977 418.0000 -0.1437022 1.0000000
- DAT 0.068797580 0.05199131 418.0000 1.3232516 1.0000000
MCI - DAT 0.074659158 0.05610088 418.0000 1.3308019 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(TYRO3_NPX, na.rm = TRUE), Std=sd(TYRO3_NPX, na.rm = TRUE),
Max=max(TYRO3_NPX, na.rm = TRUE), Min=min(TYRO3_NPX, na.rm = TRUE))NA4.4. TREM2_Diag
(TREM2_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = TREM2_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TREM2 (NPX)") +
scale_y_continuous(breaks = seq(0, 7, by = 1), limits = c(0,7)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TREM2_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TREM2_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TREM2_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
Diag 2.480042924 3 0.826680975 1.52492198 0.2074064
Age 11.232348359 1 11.232348359 20.71954646 0.0000070
sex 1.635500313 1 1.635500313 3.01689581 0.0831377
bmi 0.127087819 1 0.127087819 0.23443023 0.6285117
E4_Positive 0.006132992 1 0.006132992 0.01131311 0.9153453
Residuals 226.603493669 418 0.542113621
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
─────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.161511144 0.09267010 418.0000 1.74286139 0.4925591
- MCI -0.001873218 0.10902856 418.0000 -0.01718099 1.0000000
- DAT 0.041426642 0.13669048 418.0000 0.30306896 1.0000000
SCD - MCI -0.163384362 0.09603562 418.0000 -1.70128911 0.5377942
- DAT -0.120084502 0.12240857 418.0000 -0.98101386 1.0000000
MCI - DAT 0.043299860 0.13208416 418.0000 0.32782023 1.0000000
─────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(TREM2_NPX, na.rm = TRUE), Std=sd(TREM2_NPX, na.rm = TRUE),
Max=max(TREM2_NPX, na.rm = TRUE), Min=min(TREM2_NPX, na.rm = TRUE))4.5. C1q_Diag
(C1q_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = C1q_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "C1q (NPX)") +
scale_y_continuous(breaks = seq(-4, 1, by = 1), limits = c(-4,1)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = C1q_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = C1q_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - C1q_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
Diag 0.48599086 3 0.16199695 1.00917741 0.3885176
Age 4.28499616 1 4.28499616 26.69384378 0.0000004
sex 1.06539493 1 1.06539493 6.63699215 0.0103305
bmi 0.01320162 1 0.01320162 0.08224093 0.7744253
E4_Positive 0.08078377 1 0.08078377 0.50325119 0.4784706
Residuals 67.09893153 418 0.16052376
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD -0.01563987 0.05042712 418.0000 -0.3101480 1.0000000
- MCI -0.06843072 0.05932869 418.0000 -1.1534171 1.0000000
- DAT -0.10759314 0.07438113 418.0000 -1.4465112 0.8926998
SCD - MCI -0.05279085 0.05225849 418.0000 -1.0101871 1.0000000
- DAT -0.09195327 0.06660952 418.0000 -1.3804824 1.0000000
MCI - DAT -0.03916242 0.07187457 418.0000 -0.5448717 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(C1q_NPX, na.rm = TRUE), Std=sd(C1q_NPX, na.rm = TRUE),
Max=max(C1q_NPX, na.rm = TRUE), Min=min(C1q_NPX, na.rm = TRUE))4.6. C3_Diag
(C3_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = C3_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "C3 (NPX)") +
scale_y_continuous(breaks = seq(-2.5, 5, by = 2.5), limits = c(-2.5,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = C3_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = C3_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - C3_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
Diag 2.013136 3 0.6710452 1.991733771 0.1145672
Age 1.571970 1 1.5719703 4.665775541 0.0313374
sex 4.598419 1 4.5984189 13.648598037 0.0002497
bmi 4.508262 1 4.5082624 13.381003807 0.0002867
E4_Positive 8.935991e-4 1 8.935991e-4 0.002652298 0.9589513
Residuals 140.830516 418 0.3369151
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.069458086 0.07305580 418.0000 0.9507538 1.0000000
- MCI -0.009903556 0.08595187 418.0000 -0.1152221 1.0000000
- DAT -0.161109372 0.10775895 418.0000 -1.4950904 0.8138725
SCD - MCI -0.079361642 0.07570899 418.0000 -1.0482460 1.0000000
- DAT -0.230567459 0.09649991 418.0000 -2.3893024 0.1039373
MCI - DAT -0.151205817 0.10412759 418.0000 -1.4521205 0.8833096
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(C3_NPX, na.rm = TRUE), Std=sd(C3_NPX, na.rm = TRUE),
Max=max(C3_NPX, na.rm = TRUE), Min=min(C3_NPX, na.rm = TRUE))4.7. FB_Diag
(FB_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = Factor_B_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Factor B (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = Factor_B_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = Factor_B_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - Factor_B_NPX
──────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
──────────────────────────────────────────────────────────────────────────────────
Diag 2.11169609 3 0.70389870 2.8607819 0.0366409
Age 0.05979003 1 0.05979003 0.2429983 0.6223077
sex 1.69099589 1 1.69099589 6.8725378 0.0090724
bmi 4.97683379 1 4.97683379 20.2268254 0.0000089
E4_Positive 0.13968365 1 0.13968365 0.5677017 0.4515978
Residuals 102.84938388 418 0.24605116
──────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.07863422 0.06243199 418.0000 1.2595180 1.0000000
- MCI -0.05416761 0.07345271 418.0000 -0.7374488 1.0000000
- DAT -0.13292529 0.09208859 418.0000 -1.4434501 0.8978563
SCD - MCI -0.13280183 0.06469935 418.0000 -2.0525992 0.2444014
- DAT -0.21155950 0.08246684 418.0000 -2.5653887 0.0639234
MCI - DAT -0.07875767 0.08898531 418.0000 -0.8850638 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(Factor_B_NPX, na.rm = TRUE), Std=sd(Factor_B_NPX, na.rm = TRUE),
Max=max(Factor_B_NPX, na.rm = TRUE), Min=min(Factor_B_NPX, na.rm = TRUE))NA4.8. FH_Diag
(FH_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = Factor_H_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Factor H (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = Factor_H_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = Factor_H_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - Factor_H_NPX
─────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
─────────────────────────────────────────────────────────────────────────────────────
Diag 1.974612 3 0.6582040 3.902961733 0.0090460
Age 1.731296 1 1.7312958 10.266090202 0.0014588
sex 5.274957 1 5.2749574 31.278992474 < .0000001
bmi 1.406645 1 1.4066452 8.341004910 0.0040774
E4_Positive 5.063216e-4 1 5.063216e-4 0.003002343 0.9563290
Residuals 70.492430 418 0.1686422
─────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.08031039 0.05168655 418.0000 1.5537966 0.7259383
- MCI -0.05489890 0.06081045 418.0000 -0.9027873 1.0000000
- DAT -0.11727053 0.07623883 418.0000 -1.5381995 0.7485388
SCD - MCI -0.13520929 0.05356367 418.0000 -2.5242725 0.0717789
- DAT -0.19758092 0.06827312 418.0000 -2.8939782 0.0240185
MCI - DAT -0.06237163 0.07366966 418.0000 -0.8466393 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(Factor_H_NPX, na.rm = TRUE), Std=sd(Factor_H_NPX, na.rm = TRUE),
Max=max(Factor_H_NPX, na.rm = TRUE), Min=min(Factor_H_NPX, na.rm = TRUE))4.9. MIF_Diag
(MIF_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = MIF_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "MIF (NPX)") +
scale_y_continuous(breaks = seq(2, 8, by = 2), limits = c(2,8)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = MIF_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = MIF_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - MIF_NPX
──────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
──────────────────────────────────────────────────────────────────────────────────
Diag 3.5153080 3 1.1717693 5.032927 0.0019493
Age 8.3397025 1 8.3397025 35.820287 < .0000001
sex 1.1000618 1 1.1000618 4.724932 0.0302890
bmi 1.2334483 1 1.2334483 5.297847 0.0218427
E4_Positive 0.3637876 1 0.3637876 1.562523 0.2119956
Residuals 97.3190309 418 0.2328206
──────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
─────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.173095706 0.06073027 418.0000 2.85023759 0.0275092
- MCI -0.023814681 0.07145059 418.0000 -0.33330277 1.0000000
- DAT -0.015824877 0.08957852 418.0000 -0.17665929 1.0000000
SCD - MCI -0.196910387 0.06293583 418.0000 -3.12874864 0.0112708
- DAT -0.188920583 0.08021903 418.0000 -2.35505944 0.1138869
MCI - DAT 0.007989804 0.08655982 418.0000 0.09230384 1.0000000
─────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(MIF_NPX, na.rm = TRUE), Std=sd(MIF_NPX, na.rm = TRUE),
Max=max(MIF_NPX, na.rm = TRUE), Min=min(MIF_NPX, na.rm = TRUE))4.10. TNFR1_Diag
(TNFR1_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = TNFR1_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TNFR1 (NPX)") +
scale_y_continuous(breaks = seq(1, 6, by = 1), limits = c(1,6)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TNFR1_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TNFR1_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TNFR1_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
Diag 0.916206264 3 0.305402088 2.23386267 0.0836956
Age 4.122872311 1 4.122872311 30.15673729 < .0000001
sex 1.001843341 1 1.001843341 7.32798015 0.0070672
bmi 0.207437302 1 0.207437302 1.51729953 0.2187211
E4_Positive 0.008297865 1 0.008297865 0.06069471 0.8055222
Residuals 57.146786442 418 0.136714800
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
─────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.10024002 0.04653741 418.0000 2.15396627 0.1908830
- MCI 9.373281e-4 0.05475236 418.0000 0.01711941 1.0000000
- DAT 0.04060782 0.06864373 418.0000 0.59157356 1.0000000
SCD - MCI -0.09930269 0.04822752 418.0000 -2.05904603 0.2406529
- DAT -0.05963220 0.06147159 418.0000 -0.97007751 1.0000000
MCI - DAT 0.03967049 0.06633051 418.0000 0.59807300 1.0000000
─────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(TNFR1_NPX, na.rm = TRUE), Std=sd(TNFR1_NPX, na.rm = TRUE),
Max=max(TNFR1_NPX, na.rm = TRUE), Min=min(TNFR1_NPX, na.rm = TRUE))NA4.11. TNFR2_Diag
(TNFR2_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = TNFR2_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TNFR2 (NPX)") +
scale_y_continuous(breaks = seq(-1, 4, by = 1), limits = c(-1,4)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TNFR2_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TNFR2_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TNFR2_NPX
──────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
──────────────────────────────────────────────────────────────────────────────────
Diag 1.5060149 3 0.5020050 3.198048 0.0233632
Age 7.9232444 1 7.9232444 50.475428 < .0000001
sex 2.3658934 1 2.3658934 15.072043 0.0001202
bmi 0.2060290 1 0.2060290 1.312518 0.2525947
E4_Positive 0.4020182 1 0.4020182 2.561077 0.1102794
Residuals 65.6144243 418 0.1569723
──────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.09658881 0.04986617 418.0000 1.9369607 0.3205418
- MCI -0.03104281 0.05866872 418.0000 -0.5291203 1.0000000
- DAT -0.05060889 0.07355372 418.0000 -0.6880534 1.0000000
SCD - MCI -0.12763162 0.05167717 418.0000 -2.4697873 0.0835068
- DAT -0.14719770 0.06586856 418.0000 -2.2347186 0.1557816
MCI - DAT -0.01956608 0.07107504 418.0000 -0.2752876 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(TNFR2_NPX, na.rm = TRUE), Std=sd(TNFR2_NPX, na.rm = TRUE),
Max=max(TNFR2_NPX, na.rm = TRUE), Min=min(TNFR2_NPX, na.rm = TRUE))NA4.12. ICAM1_Diag
(ICAM1_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = ICAM1_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "ICAM1 (NPX)") +
scale_y_continuous(breaks = seq(-6,0, by = 1), limits = c(-6, 0)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = ICAM1_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = ICAM1_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - ICAM1_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
Diag 2.241751226 3 0.747250409 4.67725340 0.0031639
Age 2.001307948 1 2.001307948 12.52675716 0.0004462
sex 1.518533220 1 1.518533220 9.50493246 0.0021850
bmi 0.312637989 1 0.312637989 1.95689033 0.1625878
E4_Positive 0.005698476 1 0.005698476 0.03566839 0.8502936
Residuals 66.780788666 418 0.159762652
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.03708414 0.05030743 418.0000 0.7371504 1.0000000
- MCI -0.10784006 0.05918787 418.0000 -1.8219959 0.4150204
- DAT -0.17224326 0.07420459 418.0000 -2.3211942 0.1245392
SCD - MCI -0.14492420 0.05213445 418.0000 -2.7798162 0.0341072
- DAT -0.20932740 0.06645142 418.0000 -3.1500815 0.0104972
MCI - DAT -0.06440320 0.07170397 418.0000 -0.8981817 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(ICAM1_NPX, na.rm = TRUE), Std=sd(ICAM1_NPX, na.rm = TRUE),
Max=max(ICAM1_NPX, na.rm = TRUE), Min=min(ICAM1_NPX, na.rm = TRUE))4.13. VCAM1_Diag
(VCAM1_Diag_plot <- ggplot(DC_thesis_o,
aes(x = Diag, y = VCAM1_NPX,
colour = Diag, fill = Diag)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "VCAM1 (NPX)") +
scale_y_continuous(breaks = seq(-4,1, by = 1), limits = c(-4, 1)) +
scale_colour_manual(values = c("black","black", "black", "black")) +
scale_fill_manual(values = c("honeydew3","indianred1", "#1ca9c9", "springgreen4")) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = VCAM1_NPX ~ Diag +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = VCAM1_NPX ~ Diag,
postHocCorr = "bonf")
ANCOVA
ANCOVA - VCAM1_NPX
───────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────
Diag 0.62275236 3 0.20758412 1.64940326 0.1773703
Age 3.21055122 1 3.21055122 25.51010963 0.0000007
sex 3.56111026 1 3.56111026 28.29555018 0.0000002
bmi 0.01165933 1 0.01165933 0.09264166 0.7609968
E4_Positive 0.01120821 1 0.01120821 0.08905717 0.7655275
Residuals 52.60700289 418 0.12585407
───────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - Diag
────────────────────────────────────────────────────────────────────────────────────────────────
Diag Diag Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────
CN - SCD 0.04088060 0.04465068 418.0000 0.9155648 1.0000000
- MCI -0.04085548 0.05253258 418.0000 -0.7777170 1.0000000
- DAT -0.06483532 0.06586076 418.0000 -0.9844302 1.0000000
SCD - MCI -0.08173608 0.04627227 418.0000 -1.7664158 0.4683356
- DAT -0.10571592 0.05897939 418.0000 -1.7924213 0.4427312
MCI - DAT -0.02397984 0.06364133 418.0000 -0.3767967 1.0000000
────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(Diag)%>%
summarise(Median=median(VCAM1_NPX, na.rm = TRUE), Std=sd(VCAM1_NPX, na.rm = TRUE),
Max=max(VCAM1_NPX, na.rm = TRUE), Min=min(VCAM1_NPX, na.rm = TRUE))5. Diagnosis + Tau scheme
5.1. YKL40_Diag+T
(YKL40_diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = YKL40_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "YKL40 (NPX)") +
scale_y_continuous(breaks = seq(3,9, by = 1), limits = c(3,9)) +
scale_x_discrete(labels = c('CN T-', 'CN T+', "SCD T-", "SCD T+", "MCI T-", "MCI T+",
'DAT T-','DAT T+')) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = YKL40_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = YKL40_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - YKL40_NPX
──────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
──────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 13.0638520 7 1.8662646 10.9115261 < .0000001
Age 9.6497683 1 9.6497683 56.4194918 < .0000001
sex 0.9043688 1 0.9043688 5.2875908 0.0219749
bmi 0.1933684 1 0.1933684 1.1305711 0.2882734
E4_Positive 0.1522449 1 0.1522449 0.8901332 0.3459914
Residuals 70.8089341 414 0.1710361
──────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.275223009 0.10582820 414.0000 -2.60065859 0.2698522
- SCD_T- 0.109988541 0.05705852 414.0000 1.92764443 1.0000000
- SCD_T+ -0.320932151 0.09045350 414.0000 -3.54803445 0.0121117
- MCI_T- -0.055590936 0.07643626 414.0000 -0.72728488 1.0000000
- MCI_T+ -0.345237912 0.07996944 414.0000 -4.31712317 0.0005544
- DAT_T- -0.004974409 0.11398059 414.0000 -0.04364259 1.0000000
- DAT_T+ -0.372832857 0.09008856 414.0000 -4.13851487 0.0011863
CN_T+ - SCD_T- 0.385211550 0.10159586 414.0000 3.79160659 0.0048143
- SCD_T+ -0.045709142 0.12207518 414.0000 -0.37443436 1.0000000
- MCI_T- 0.219632073 0.11373039 414.0000 1.93116432 1.0000000
- MCI_T+ -0.070014903 0.11488944 414.0000 -0.60941114 1.0000000
- DAT_T- 0.270248600 0.14042946 414.0000 1.92444379 1.0000000
- DAT_T+ -0.097609848 0.12122003 414.0000 -0.80522869 1.0000000
SCD_T- - SCD_T+ -0.430920692 0.08373018 414.0000 -5.14653976 0.0000115
- MCI_T- -0.165579477 0.06975152 414.0000 -2.37384751 0.5056577
- MCI_T+ -0.455226453 0.07287684 414.0000 -6.24651729 < .0000001
- DAT_T- -0.114962950 0.10791714 414.0000 -1.06528910 1.0000000
- DAT_T+ -0.482821398 0.08194664 414.0000 -5.89189958 0.0000002
SCD_T+ - MCI_T- 0.265341215 0.09726255 414.0000 2.72809240 0.1859578
- MCI_T+ -0.024305761 0.09886704 414.0000 -0.24584291 1.0000000
- DAT_T- 0.315957742 0.12658772 414.0000 2.49595896 0.3625955
- DAT_T+ -0.051900706 0.10478031 414.0000 -0.49532880 1.0000000
MCI_T- - MCI_T+ -0.289646976 0.08838043 414.0000 -3.27727490 0.0318225
- DAT_T- 0.050616527 0.11874860 414.0000 0.42624945 1.0000000
- DAT_T+ -0.317241921 0.09576211 414.0000 -3.31281241 0.0281338
MCI_T+ - DAT_T- 0.340263503 0.11962920 414.0000 2.84431818 0.1307988
- DAT_T+ -0.027594945 0.09534928 414.0000 -0.28940906 1.0000000
DAT_T- - DAT_T+ -0.367858448 0.12299203 414.0000 -2.99091288 0.0825329
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(YKL40_NPX, na.rm = TRUE), Std=sd(YKL40_NPX, na.rm = TRUE),
Max=max(YKL40_NPX, na.rm = TRUE), Min=min(YKL40_NPX, na.rm = TRUE))NA5.2. Axl_Diag+T
(AXL_diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = AXL_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "AXL (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = AXL_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = AXL_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - AXL_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 9.1842515 7 1.3120359 8.514496 < .0000001
Age 1.1123074 1 1.1123074 7.218352 0.0075068
sex 0.9746999 1 0.9746999 6.325344 0.0122803
bmi 0.2990524 1 0.2990524 1.940710 0.1643391
E4_Positive 0.2396285 1 0.2396285 1.555076 0.2130926
Residuals 63.7950704 414 0.1540944
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.27367273 0.10045023 414.0000 -2.7244610 0.1879780
- SCD_T- 0.10465433 0.05415893 414.0000 1.9323561 1.0000000
- SCD_T+ -0.31680021 0.08585685 414.0000 -3.6898655 0.0071214
- MCI_T- 0.12251190 0.07255193 414.0000 1.6886099 1.0000000
- MCI_T+ -0.18551496 0.07590556 414.0000 -2.4440235 0.4183461
- DAT_T- 0.24681578 0.10818833 414.0000 2.2813530 0.6449693
- DAT_T+ -0.08089916 0.08551045 414.0000 -0.9460734 1.0000000
CN_T+ - SCD_T- 0.37832707 0.09643297 414.0000 3.9232126 0.0028638
- SCD_T+ -0.04312748 0.11587157 414.0000 -0.3722007 1.0000000
- MCI_T- 0.39618464 0.10795085 414.0000 3.6700465 0.0076779
- MCI_T+ 0.08815777 0.10905100 414.0000 0.8084087 1.0000000
- DAT_T- 0.52048851 0.13329313 414.0000 3.9048414 0.0030818
- DAT_T+ 0.19277357 0.11505988 414.0000 1.6754195 1.0000000
SCD_T- - SCD_T+ -0.42145455 0.07947519 414.0000 -5.3029703 0.0000052
- MCI_T- 0.01785757 0.06620690 414.0000 0.2697237 1.0000000
- MCI_T+ -0.29016930 0.06917339 414.0000 -4.1948108 0.0009361
- DAT_T- 0.14216145 0.10243301 414.0000 1.3878480 1.0000000
- DAT_T+ -0.18555350 0.07778229 414.0000 -2.3855495 0.4900695
SCD_T+ - MCI_T- 0.43931212 0.09231987 414.0000 4.7585870 0.0000755
- MCI_T+ 0.13128525 0.09384282 414.0000 1.3989908 1.0000000
- DAT_T- 0.56361600 0.12015479 414.0000 4.6907492 0.0001037
- DAT_T+ 0.23590105 0.09945559 414.0000 2.3719234 0.5082620
MCI_T- - MCI_T+ -0.30802687 0.08388912 414.0000 -3.6718332 0.0076261
- DAT_T- 0.12430388 0.11271405 414.0000 1.1028251 1.0000000
- DAT_T+ -0.20341107 0.09089568 414.0000 -2.2378518 0.7213326
MCI_T+ - DAT_T- 0.43233074 0.11354989 414.0000 3.8074078 0.0045267
- DAT_T+ 0.10461580 0.09050383 414.0000 1.1559268 1.0000000
DAT_T- - DAT_T+ -0.32771494 0.11674183 414.0000 -2.8071766 0.1465509
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(AXL_NPX, na.rm = TRUE), Std=sd(AXL_NPX, na.rm = TRUE),
Max=max(AXL_NPX, na.rm = TRUE), Min=min(AXL_NPX, na.rm = TRUE))5.3. Tyro3_Diag+T
(Tyro3_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = TYRO3_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Tyro3 (NPX)") +
scale_y_continuous(breaks = seq(2, 6, by = 1), limits = c(2,6)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TYRO3_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TYRO3_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TYRO3_NPX
──────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
──────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 5.68315373 7 0.81187910 9.3314434 < .0000001
Age 0.92191103 1 0.92191103 10.5961104 0.0012264
sex 0.08251463 1 0.08251463 0.9483931 0.3306973
bmi 0.40616118 1 0.40616118 4.6682690 0.0312979
E4_Positive 0.07522119 1 0.07522119 0.8645650 0.3530062
Residuals 36.01993112 414 0.08700466
──────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.198816574 0.07547946 414.0000 -2.6340486 0.2451007
- SCD_T- 0.091749234 0.04069564 414.0000 2.2545222 0.6911879
- SCD_T+ -0.187656450 0.06451383 414.0000 -2.9087787 0.1070692
- MCI_T- 0.167786241 0.05451636 414.0000 3.0777228 0.0622877
- MCI_T+ -0.112710410 0.05703631 414.0000 -1.9761167 1.0000000
- DAT_T- 0.270833375 0.08129397 414.0000 3.3315311 0.0263546
- DAT_T+ 0.008125375 0.06425354 414.0000 0.1264580 1.0000000
CN_T+ - SCD_T- 0.290565809 0.07246085 414.0000 4.0099695 0.0020172
- SCD_T+ 0.011160124 0.08706724 414.0000 0.1281782 1.0000000
- MCI_T- 0.366602815 0.08111552 414.0000 4.5195152 0.0002268
- MCI_T+ 0.086106164 0.08194218 414.0000 1.0508161 1.0000000
- DAT_T- 0.469649950 0.10015800 414.0000 4.6890909 0.0001045
- DAT_T+ 0.206941949 0.08645733 414.0000 2.3935733 0.4796270
SCD_T- - SCD_T+ -0.279405685 0.05971857 414.0000 -4.6787066 0.0001096
- MCI_T- 0.076037007 0.04974863 414.0000 1.5284242 1.0000000
- MCI_T+ -0.204459645 0.05197769 414.0000 -3.9336041 0.0027470
- DAT_T- 0.179084141 0.07696935 414.0000 2.3266942 0.5729721
- DAT_T+ -0.083623860 0.05844651 414.0000 -1.4307759 1.0000000
SCD_T+ - MCI_T- 0.355442692 0.06937022 414.0000 5.1238516 0.0000129
- MCI_T+ 0.074946040 0.07051458 414.0000 1.0628445 1.0000000
- DAT_T- 0.458489826 0.09028570 414.0000 5.0782109 0.0000162
- DAT_T+ 0.195781825 0.07473208 414.0000 2.6197828 0.2554153
MCI_T- - MCI_T+ -0.280496651 0.06303526 414.0000 -4.4498374 0.0003097
- DAT_T- 0.103047134 0.08469464 414.0000 1.2166902 1.0000000
- DAT_T+ -0.159660866 0.06830007 414.0000 -2.3376385 0.5566857
MCI_T+ - DAT_T- 0.383543785 0.08532270 414.0000 4.4952137 0.0002529
- DAT_T+ 0.120835785 0.06800562 414.0000 1.7768499 1.0000000
DAT_T- - DAT_T+ -0.262708001 0.08772116 414.0000 -2.9948075 0.0815088
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(TYRO3_NPX, na.rm = TRUE), Std=sd(TYRO3_NPX, na.rm = TRUE),
Max=max(TYRO3_NPX, na.rm = TRUE), Min=min(TYRO3_NPX, na.rm = TRUE))5.4. TREM2_Diag+T
(TREM2_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = TREM2_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TREM2 (NPX)") +
scale_y_continuous(breaks = seq(0, 7, by = 1), limits = c(0,7)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TREM2_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TREM2_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TREM2_NPX
─────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
─────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 21.4878874 7 3.0696982 6.1217808 0.0000008
Age 8.6051038 1 8.6051038 17.1608268 0.0000417
sex 1.0259169 1 1.0259169 2.0459465 0.1533663
bmi 0.9296899 1 0.9296899 1.8540448 0.1740542
E4_Positive 0.4779251 1 0.4779251 0.9531076 0.3294996
Residuals 207.5956491 414 0.5014388
─────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.47386918 0.18120346 414.0000 -2.6151221 0.2588684
- SCD_T- 0.16324659 0.09769799 414.0000 1.6709310 1.0000000
- SCD_T+ -0.44346985 0.15487827 414.0000 -2.8633445 0.1233403
- MCI_T- 0.09219064 0.13087736 414.0000 0.7044048 1.0000000
- MCI_T+ -0.33600842 0.13692701 414.0000 -2.4539235 0.4071680
- DAT_T- 0.26051907 0.19516233 414.0000 1.3348840 1.0000000
- DAT_T+ -0.27071415 0.15425340 414.0000 -1.7549963 1.0000000
CN_T+ - SCD_T- 0.63711578 0.17395669 414.0000 3.6624966 0.0079005
- SCD_T+ 0.03039933 0.20902223 414.0000 0.1454359 1.0000000
- MCI_T- 0.56605983 0.19473393 414.0000 2.9068372 0.1077224
- MCI_T+ 0.13786076 0.19671850 414.0000 0.7008022 1.0000000
- DAT_T- 0.73438825 0.24044919 414.0000 3.0542347 0.0672592
- DAT_T+ 0.20315503 0.20755801 414.0000 0.9787868 1.0000000
SCD_T- - SCD_T+ -0.60671645 0.14336631 414.0000 -4.2319318 0.0007996
- MCI_T- -0.07105595 0.11943147 414.0000 -0.5949516 1.0000000
- MCI_T+ -0.49925502 0.12478278 414.0000 -4.0009931 0.0020923
- DAT_T- 0.09727247 0.18478023 414.0000 0.5264225 1.0000000
- DAT_T+ -0.43396074 0.14031247 414.0000 -3.0928167 0.0592738
SCD_T+ - MCI_T- 0.53566050 0.16653700 414.0000 3.2164654 0.0391916
- MCI_T+ 0.10746143 0.16928428 414.0000 0.6347986 1.0000000
- DAT_T- 0.70398892 0.21674878 414.0000 3.2479487 0.0351991
- DAT_T+ 0.17275570 0.17940923 414.0000 0.9629143 1.0000000
MCI_T- - MCI_T+ -0.42819907 0.15132867 414.0000 -2.8295964 0.1368486
- DAT_T- 0.16832842 0.20332632 414.0000 0.8278732 1.0000000
- DAT_T+ -0.36290479 0.16396790 414.0000 -2.2132674 0.7678679
MCI_T+ - DAT_T- 0.59652749 0.20483411 414.0000 2.9122468 0.1059114
- DAT_T+ 0.06529427 0.16326102 414.0000 0.3999379 1.0000000
DAT_T- - DAT_T+ -0.53123322 0.21059210 414.0000 -2.5225696 0.3366702
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(TREM2_NPX, na.rm = TRUE), Std=sd(TREM2_NPX, na.rm = TRUE),
Max=max(TREM2_NPX, na.rm = TRUE), Min=min(TREM2_NPX, na.rm = TRUE))5.5. C1q_Diag+T
(C1q_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = C1q_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "C1q (NPX)") +
scale_y_continuous(breaks = seq(-4, 1, by = 1), limits = c(-4,1)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = C1q_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = C1q_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - C1q_NPX
───────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 5.02026935 7 0.71718134 4.745699988 0.0000382
Age 3.54484724 1 3.54484724 23.456803286 0.0000018
sex 0.83094859 1 0.83094859 5.498515506 0.0195042
bmi 0.02363702 1 0.02363702 0.156409829 0.6926874
E4_Positive 8.361946e-4 1 8.361946e-4 0.005533229 0.9407394
Residuals 62.56465304 414 0.15112235
───────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.199254731 0.09947682 414.0000 -2.00302676 1.0000000
- SCD_T- -0.011093473 0.05363410 414.0000 -0.20683619 1.0000000
- SCD_T+ -0.292056629 0.08502485 414.0000 -3.43495599 0.0182699
- MCI_T- -0.036107651 0.07184887 414.0000 -0.50255004 1.0000000
- MCI_T+ -0.203620965 0.07517000 414.0000 -2.70880635 0.1969155
- DAT_T- 0.078726778 0.10713994 414.0000 0.73480328 1.0000000
- DAT_T+ -0.287767143 0.08468181 414.0000 -3.39821659 0.0208313
CN_T+ - SCD_T- 0.188161257 0.09549849 414.0000 1.97030601 1.0000000
- SCD_T+ -0.092801898 0.11474873 414.0000 -0.80874013 1.0000000
- MCI_T- 0.163147080 0.10690476 414.0000 1.52609750 1.0000000
- MCI_T+ -0.004366235 0.10799424 414.0000 -0.04043026 1.0000000
- DAT_T- 0.277981509 0.13200145 414.0000 2.10589733 1.0000000
- DAT_T+ -0.088512413 0.11394490 414.0000 -0.77680013 1.0000000
SCD_T- - SCD_T+ -0.280963156 0.07870503 414.0000 -3.56982449 0.0111752
- MCI_T- -0.025014177 0.06556532 414.0000 -0.38151537 1.0000000
- MCI_T+ -0.192527492 0.06850307 414.0000 -2.81049435 0.1450769
- DAT_T- 0.089820251 0.10144039 414.0000 0.88544860 1.0000000
- DAT_T+ -0.276673670 0.07702854 414.0000 -3.59183325 0.0102986
SCD_T+ - MCI_T- 0.255948978 0.09142524 414.0000 2.79954383 0.1499937
- MCI_T+ 0.088435664 0.09293344 414.0000 0.95160214 1.0000000
- DAT_T- 0.370783407 0.11899044 414.0000 3.11607740 0.0548910
- DAT_T+ 0.004289486 0.09849182 414.0000 0.04355169 1.0000000
MCI_T- - MCI_T+ -0.167513315 0.08307620 414.0000 -2.01638154 1.0000000
- DAT_T- 0.114834429 0.11162179 414.0000 1.02878142 1.0000000
- DAT_T+ -0.251659492 0.09001486 414.0000 -2.79575492 0.1517298
MCI_T+ - DAT_T- 0.282347743 0.11244954 414.0000 2.51088393 0.3478447
- DAT_T+ -0.084146178 0.08962680 414.0000 -0.93885060 1.0000000
DAT_T- - DAT_T+ -0.366493921 0.11561055 414.0000 -3.17007336 0.0458432
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(C1q_NPX, na.rm = TRUE), Std=sd(C1q_NPX, na.rm = TRUE),
Max=max(C1q_NPX, na.rm = TRUE), Min=min(C1q_NPX, na.rm = TRUE))5.6. C3_Diag+T
(C3_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = C3_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "C3 (NPX)") +
scale_y_continuous(breaks = seq(-2.5, 5, by = 2.5), limits = c(-2.5,5)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = C3_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = C3_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - C3_NPX
───────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 3.339599 7 0.4770856 1.415825775 0.1970620
Age 1.443481 1 1.4434810 4.283754533 0.0390980
sex 4.247121 1 4.2471212 12.603993630 0.0004291
bmi 4.144897 1 4.1448972 12.300627811 0.0005024
E4_Positive 9.572331e-4 1 9.572331e-4 0.002840738 0.9575197
Residuals 139.504052 414 0.3369663
───────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ 0.066362115 0.14854252 414.0000 0.44675502 1.0000000
- SCD_T- 0.108694599 0.08008845 414.0000 1.35718193 1.0000000
- SCD_T+ -0.061362393 0.12696230 414.0000 -0.48331192 1.0000000
- MCI_T- -0.056652486 0.10728742 414.0000 -0.52804406 1.0000000
- MCI_T+ 0.063073852 0.11224666 414.0000 0.56192186 1.0000000
- DAT_T- -0.245473293 0.15998538 414.0000 -1.53434833 1.0000000
- DAT_T+ -0.102434019 0.12645006 414.0000 -0.81007489 1.0000000
CN_T+ - SCD_T- 0.042332484 0.14260193 414.0000 0.29685771 1.0000000
- SCD_T+ -0.127724508 0.17134710 414.0000 -0.74541388 1.0000000
- MCI_T- -0.123014601 0.15963419 414.0000 -0.77060309 1.0000000
- MCI_T+ -0.003288263 0.16126105 414.0000 -0.02039093 1.0000000
- DAT_T- -0.311835408 0.19710952 414.0000 -1.58204132 1.0000000
- DAT_T+ -0.168796134 0.17014680 414.0000 -0.99206178 1.0000000
SCD_T- - SCD_T+ -0.170056992 0.11752531 414.0000 -1.44698188 1.0000000
- MCI_T- -0.165347086 0.09790459 414.0000 -1.68885930 1.0000000
- MCI_T+ -0.045620747 0.10229135 414.0000 -0.44598830 1.0000000
- DAT_T- -0.354167893 0.15147460 414.0000 -2.33813394 0.5559581
- DAT_T+ -0.211128619 0.11502191 414.0000 -1.83555140 1.0000000
SCD_T+ - MCI_T- 0.004709906 0.13651960 414.0000 0.03449985 1.0000000
- MCI_T+ 0.124436245 0.13877170 414.0000 0.89669754 1.0000000
- DAT_T- -0.184110901 0.17768098 414.0000 -1.03618799 1.0000000
- DAT_T+ -0.041071627 0.14707168 414.0000 -0.27926264 1.0000000
MCI_T- - MCI_T+ 0.119726338 0.12405250 414.0000 0.96512639 1.0000000
- DAT_T- -0.188820807 0.16667785 414.0000 -1.13284882 1.0000000
- DAT_T+ -0.045781533 0.13441357 414.0000 -0.34060202 1.0000000
MCI_T+ - DAT_T- -0.308547145 0.16791387 414.0000 -1.83753220 1.0000000
- DAT_T+ -0.165507871 0.13383410 414.0000 -1.23666439 1.0000000
DAT_T- - DAT_T+ 0.143039274 0.17263401 414.0000 0.82856950 1.0000000
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(C3_NPX, na.rm = TRUE), Std=sd(C3_NPX, na.rm = TRUE),
Max=max(C3_NPX, na.rm = TRUE), Min=min(C3_NPX, na.rm = TRUE))5.7. FB_Diag+T
(FB_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = Factor_B_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Factor B (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = Factor_B_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = Factor_B_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - Factor_B_NPX
──────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
──────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 3.36507653 7 0.48072522 1.95893769 0.0593499
Age 0.02160853 1 0.02160853 0.08805396 0.7668147
sex 1.38135992 1 1.38135992 5.62899116 0.0181219
bmi 5.05300243 1 5.05300243 20.59080017 0.0000075
E4_Positive 0.15916449 1 0.15916449 0.64858946 0.4210797
Residuals 101.59600344 414 0.24540097
──────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.087992237 0.12676393 414.0000 -0.69414257 1.0000000
- SCD_T- 0.093223808 0.06834627 414.0000 1.36399268 1.0000000
- SCD_T+ -0.106365223 0.10834770 414.0000 -0.98170267 1.0000000
- MCI_T- -0.115430209 0.09155745 414.0000 -1.26074069 1.0000000
- MCI_T+ -0.029858272 0.09578959 414.0000 -0.31170684 1.0000000
- DAT_T- -0.168999214 0.13652909 414.0000 -1.23782571 1.0000000
- DAT_T+ -0.149441029 0.10791056 414.0000 -1.38486011 1.0000000
CN_T+ - SCD_T- 0.181216045 0.12169432 414.0000 1.48910846 1.0000000
- SCD_T+ -0.018372986 0.14622501 414.0000 -0.12564872 1.0000000
- MCI_T- -0.027437972 0.13622939 414.0000 -0.20141007 1.0000000
- MCI_T+ 0.058133965 0.13761773 414.0000 0.42243079 1.0000000
- DAT_T- -0.081006977 0.16821027 414.0000 -0.48158164 1.0000000
- DAT_T+ -0.061448792 0.14520069 414.0000 -0.42319903 1.0000000
SCD_T- - SCD_T+ -0.199589031 0.10029431 414.0000 -1.99003342 1.0000000
- MCI_T- -0.208654016 0.08355029 414.0000 -2.49734633 0.3612013
- MCI_T+ -0.123082079 0.08729389 414.0000 -1.40997365 1.0000000
- DAT_T- -0.262223022 0.12926612 414.0000 -2.02855187 1.0000000
- DAT_T+ -0.242664836 0.09815794 414.0000 -2.47218742 0.3872381
SCD_T+ - MCI_T- -0.009064986 0.11650375 414.0000 -0.07780853 1.0000000
- MCI_T+ 0.076506951 0.11842566 414.0000 0.64603355 1.0000000
- DAT_T- -0.062633991 0.15163025 414.0000 -0.41307056 1.0000000
- DAT_T+ -0.043075806 0.12550874 414.0000 -0.34320961 1.0000000
MCI_T- - MCI_T+ 0.085571937 0.10586451 414.0000 0.80831558 1.0000000
- DAT_T- -0.053569006 0.14224034 414.0000 -0.37660908 1.0000000
- DAT_T+ -0.034010820 0.11470650 414.0000 -0.29650300 1.0000000
MCI_T+ - DAT_T- -0.139140943 0.14329514 414.0000 -0.97100947 1.0000000
- DAT_T+ -0.119582757 0.11421199 414.0000 -1.04702455 1.0000000
DAT_T- - DAT_T+ 0.019558186 0.14732324 414.0000 0.13275696 1.0000000
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(Factor_B_NPX, na.rm = TRUE), Std=sd(Factor_B_NPX, na.rm = TRUE),
Max=max(Factor_B_NPX, na.rm = TRUE), Min=min(Factor_B_NPX, na.rm = TRUE))5.8. FH_Diag+T
(FH_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = Factor_H_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "Factor H (NPX)") +
scale_y_continuous(breaks = seq(0, 5, by = 1), limits = c(0,5)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = Factor_H_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = Factor_H_ng_ml ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - Factor_H_NPX
─────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
─────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 4.91475893 7 0.70210842 4.3029321 0.0001303
Age 1.31662580 1 1.31662580 8.0690549 0.0047250
sex 4.68372438 1 4.68372438 28.7046093 0.0000001
bmi 1.91378467 1 1.91378467 11.7287946 0.0006768
E4_Positive 0.04179002 1 0.04179002 0.2561137 0.6130721
Residuals 67.55228292 414 0.16316977
─────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.16641392 0.10336592 414.0000 -1.60994959 1.0000000
- SCD_T- 0.09003308 0.05573096 414.0000 1.61549498 1.0000000
- SCD_T+ -0.18165196 0.08834895 414.0000 -2.05607378 1.0000000
- MCI_T- -0.03946015 0.07465784 414.0000 -0.52854658 1.0000000
- MCI_T+ -0.15546294 0.07810881 414.0000 -1.99033802 1.0000000
- DAT_T- -0.02550874 0.11132864 414.0000 -0.22913006 1.0000000
- DAT_T+ -0.23634099 0.08799250 414.0000 -2.68592201 0.2106704
CN_T+ - SCD_T- 0.25644701 0.09923206 414.0000 2.58431599 0.2827633
- SCD_T+ -0.01523803 0.11923489 414.0000 -0.12779844 1.0000000
- MCI_T- 0.12695378 0.11108426 414.0000 1.14286021 1.0000000
- MCI_T+ 0.01095099 0.11221634 414.0000 0.09758817 1.0000000
- DAT_T- 0.14090519 0.13716213 414.0000 1.02728932 1.0000000
- DAT_T+ -0.06992706 0.11839964 414.0000 -0.59060198 1.0000000
SCD_T- - SCD_T+ -0.27168504 0.08178205 414.0000 -3.32206189 0.0272412
- MCI_T- -0.12949323 0.06812863 414.0000 -1.90071664 1.0000000
- MCI_T+ -0.24549602 0.07118124 414.0000 -3.44888665 0.0173780
- DAT_T- -0.11554182 0.10540626 414.0000 -1.09615709 1.0000000
- DAT_T+ -0.32637407 0.08004001 414.0000 -4.07763628 0.0015280
SCD_T+ - MCI_T- 0.14219181 0.09499957 414.0000 1.49676274 1.0000000
- MCI_T+ 0.02618902 0.09656673 414.0000 0.27120128 1.0000000
- DAT_T- 0.15614322 0.12364244 414.0000 1.26286108 1.0000000
- DAT_T+ -0.05468903 0.10234242 414.0000 -0.53437305 1.0000000
MCI_T- - MCI_T+ -0.11600279 0.08632411 414.0000 -1.34380523 1.0000000
- DAT_T- 0.01395141 0.11598571 414.0000 0.12028557 1.0000000
- DAT_T+ -0.19688084 0.09353404 414.0000 -2.10491102 1.0000000
MCI_T+ - DAT_T- 0.12995420 0.11684582 414.0000 1.11218527 1.0000000
- DAT_T+ -0.08087805 0.09313081 414.0000 -0.86843490 1.0000000
DAT_T- - DAT_T+ -0.21083225 0.12013041 414.0000 -1.75502813 1.0000000
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(Factor_H_NPX, na.rm = TRUE), Std=sd(Factor_H_NPX, na.rm = TRUE),
Max=max(Factor_H_NPX, na.rm = TRUE), Min=min(Factor_H_NPX, na.rm = TRUE))5.9. MIF_Diag+T
(MIF_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = MIF_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "MIF (NPX)") +
scale_y_continuous(breaks = seq(2, 8, by = 2), limits = c(2,8)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = MIF_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = MIF_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - MIF_NPX
────────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 22.725758494 7 3.246536928 17.207665026 < .0000001
Age 6.207199746 1 6.207199746 32.900107516 < .0000001
sex 0.695055305 1 0.695055305 3.684011343 0.0556236
bmi 0.205320675 1 0.205320675 1.088264042 0.2974649
E4_Positive 0.001490990 1 0.001490990 0.007902716 0.9292066
Residuals 78.108580449 414 0.188668069
────────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.45404715 0.11114930 414.0000 -4.0850202 0.0014820
- SCD_T- 0.16876106 0.05992746 414.0000 2.8160891 0.1426216
- SCD_T+ -0.37750170 0.09500156 414.0000 -3.9736368 0.0023378
- MCI_T- 0.12878756 0.08027952 414.0000 1.6042393 1.0000000
- MCI_T+ -0.41317630 0.08399035 414.0000 -4.9193306 0.0000351
- DAT_T- 0.19426132 0.11971160 414.0000 1.6227443 1.0000000
- DAT_T+ -0.31889956 0.09461827 414.0000 -3.3703804 0.0229908
CN_T+ - SCD_T- 0.62280821 0.10670417 414.0000 5.8367750 0.0000003
- SCD_T+ 0.07654544 0.12821319 414.0000 0.5970169 1.0000000
- MCI_T- 0.58283471 0.11944882 414.0000 4.8793675 0.0000426
- MCI_T+ 0.04087085 0.12066615 414.0000 0.3387102 1.0000000
- DAT_T- 0.64830847 0.14749034 414.0000 4.3955996 0.0003936
- DAT_T+ 0.13514759 0.12731505 414.0000 1.0615209 1.0000000
SCD_T- - SCD_T+ -0.54626276 0.08794018 414.0000 -6.2117539 < .0000001
- MCI_T- -0.03997350 0.07325867 414.0000 -0.5456487 1.0000000
- MCI_T+ -0.58193736 0.07654113 414.0000 -7.6029363 < .0000001
- DAT_T- 0.02550026 0.11334328 414.0000 0.2249826 1.0000000
- DAT_T+ -0.48766062 0.08606697 414.0000 -5.6660600 0.0000008
SCD_T+ - MCI_T- 0.50628927 0.10215297 414.0000 4.9561876 0.0000294
- MCI_T+ -0.03567459 0.10383814 414.0000 -0.3435597 1.0000000
- DAT_T- 0.57176303 0.13295262 414.0000 4.3005021 0.0005958
- DAT_T+ 0.05860214 0.11004873 414.0000 0.5325109 1.0000000
MCI_T- - MCI_T+ -0.54196386 0.09282425 414.0000 -5.8386018 0.0000003
- DAT_T- 0.06547376 0.12471935 414.0000 0.5249687 1.0000000
- DAT_T+ -0.44768712 0.10057709 414.0000 -4.4511838 0.0003079
MCI_T+ - DAT_T- 0.60743762 0.12564423 414.0000 4.8345844 0.0000527
- DAT_T+ 0.09427674 0.10014350 414.0000 0.9414165 1.0000000
DAT_T- - DAT_T+ -0.51316088 0.12917614 414.0000 -3.9725670 0.0023480
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(MIF_NPX, na.rm = TRUE), Std=sd(MIF_NPX, na.rm = TRUE),
Max=max(MIF_NPX, na.rm = TRUE), Min=min(MIF_NPX, na.rm = TRUE))5.10. TNFR1_Diag+T
(TNFR1_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = TNFR1_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TNFR1 (NPX)") +
scale_y_continuous(breaks = seq(1, 6, by = 1), limits = c(1,6)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TNFR1_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TNFR1_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TNFR1_NPX
───────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 9.149195430 7 1.307027919 11.06251382 < .0000001
Age 3.100448919 1 3.100448919 26.24179524 0.0000005
sex 0.705644882 1 0.705644882 5.97248624 0.0149473
bmi 0.002840716 1 0.002840716 0.02404345 0.8768500
E4_Positive 0.099107499 1 0.099107499 0.83883294 0.3602639
Residuals 48.913797276 414 0.118149269
───────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.26839595 0.08795754 414.0000 -3.0514264 0.0678774
- SCD_T- 0.11067966 0.04742334 414.0000 2.3338646 0.5622553
- SCD_T+ -0.29691961 0.07517909 414.0000 -3.9494973 0.0025770
- MCI_T- 0.08298194 0.06352886 414.0000 1.3062084 1.0000000
- MCI_T+ -0.22451994 0.06646541 414.0000 -3.3779966 0.0223801
- DAT_T- 0.18219393 0.09473328 414.0000 1.9232305 1.0000000
- DAT_T+ -0.15183189 0.07487577 414.0000 -2.0277839 1.0000000
CN_T+ - SCD_T- 0.37907561 0.08443990 414.0000 4.4892951 0.0002597
- SCD_T+ -0.02852366 0.10146098 414.0000 -0.2811294 1.0000000
- MCI_T- 0.35137789 0.09452533 414.0000 3.7172882 0.0064138
- MCI_T+ 0.04387602 0.09548865 414.0000 0.4594893 1.0000000
- DAT_T- 0.45058988 0.11671586 414.0000 3.8605710 0.0036738
- DAT_T+ 0.11656406 0.10075023 414.0000 1.1569607 1.0000000
SCD_T- - SCD_T+ -0.40759927 0.06959110 414.0000 -5.8570607 0.0000003
- MCI_T- -0.02769772 0.05797294 414.0000 -0.4777698 1.0000000
- MCI_T+ -0.33519960 0.06057051 414.0000 -5.5340399 0.0000016
- DAT_T- 0.07151426 0.08969373 414.0000 0.7973162 1.0000000
- DAT_T+ -0.26251155 0.06810874 414.0000 -3.8543006 0.0037658
SCD_T+ - MCI_T- 0.37990155 0.08083832 414.0000 4.6995228 0.0000996
- MCI_T+ 0.07239967 0.08217188 414.0000 0.8810761 1.0000000
- DAT_T- 0.47911354 0.10521150 414.0000 4.5538133 0.0001943
- DAT_T+ 0.14508772 0.08708660 414.0000 1.6660166 1.0000000
MCI_T- - MCI_T+ -0.30750187 0.07345609 414.0000 -4.1862001 0.0009708
- DAT_T- 0.09921199 0.09869614 414.0000 1.0052266 1.0000000
- DAT_T+ -0.23481383 0.07959126 414.0000 -2.9502463 0.0939531
MCI_T+ - DAT_T- 0.40671386 0.09942803 414.0000 4.0905351 0.0014486
- DAT_T+ 0.07268805 0.07924814 414.0000 0.9172209 1.0000000
DAT_T- - DAT_T+ -0.33402581 0.10222300 414.0000 -3.2676189 0.0328996
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(TNFR1_NPX, na.rm = TRUE), Std=sd(TNFR1_NPX, na.rm = TRUE),
Max=max(TNFR1_NPX, na.rm = TRUE), Min=min(TNFR1_NPX, na.rm = TRUE))5.11. TNFR2_Diag+T
(TNFR2_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = TNFR2_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "TNFR2 (NPX)") +
scale_y_continuous(breaks = seq(-1, 4, by = 1), limits = c(-1,4)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = TNFR2_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = TNFR2_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - TNFR2_NPX
───────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
───────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 11.39064174 7 1.62723453 12.0882387 < .0000001
Age 6.32233279 1 6.32233279 46.9667197 < .0000001
sex 1.85440798 1 1.85440798 13.7758423 0.0002341
bmi 1.267309e-6 1 1.267309e-6 9.414456e-6 0.9975533
E4_Positive 0.03407541 1 0.03407541 0.2531360 0.6151431
Residuals 55.72979748 414 0.13461304
───────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.31061888 0.09388606 414.0000 -3.30846658 0.0285626
- SCD_T- 0.10288733 0.05061978 414.0000 2.03255203 1.0000000
- SCD_T+ -0.33082091 0.08024632 414.0000 -4.12256823 0.0012680
- MCI_T- 0.06834490 0.06781084 414.0000 1.00787564 1.0000000
- MCI_T+ -0.29450195 0.07094532 414.0000 -4.15111178 0.0011253
- DAT_T- 0.07867033 0.10111850 414.0000 0.77800135 1.0000000
- DAT_T+ -0.25378164 0.07992256 414.0000 -3.17534445 0.0450381
CN_T+ - SCD_T- 0.41350621 0.09013132 414.0000 4.58781927 0.0001665
- SCD_T+ -0.02020203 0.10829966 414.0000 -0.18653826 1.0000000
- MCI_T- 0.37896378 0.10089653 414.0000 3.75596437 0.0055276
- MCI_T+ 0.01611693 0.10192479 414.0000 0.15812575 1.0000000
- DAT_T- 0.38928921 0.12458275 414.0000 3.12474398 0.0533358
- DAT_T+ 0.05683724 0.10754101 414.0000 0.52851690 1.0000000
SCD_T- - SCD_T+ -0.43370824 0.07428168 414.0000 -5.83869721 0.0000003
- MCI_T- -0.03454243 0.06188044 414.0000 -0.55821246 1.0000000
- MCI_T+ -0.39738928 0.06465308 414.0000 -6.14648599 < .0000001
- DAT_T- -0.02421700 0.09573927 414.0000 -0.25294741 1.0000000
- DAT_T+ -0.35666897 0.07269941 414.0000 -4.90607804 0.0000375
SCD_T+ - MCI_T- 0.39916581 0.08628699 414.0000 4.62602517 0.0001398
- MCI_T+ 0.03631896 0.08771043 414.0000 0.41407804 1.0000000
- DAT_T- 0.40949124 0.11230298 414.0000 3.64630798 0.0083983
- DAT_T+ 0.07703927 0.09295642 414.0000 0.82876761 1.0000000
MCI_T- - MCI_T+ -0.36284684 0.07840718 414.0000 -4.62772475 0.0001387
- DAT_T- 0.01032543 0.10534847 414.0000 0.09801217 1.0000000
- DAT_T+ -0.32212654 0.08495588 414.0000 -3.79169220 0.0048127
MCI_T+ - DAT_T- 0.37317228 0.10612969 414.0000 3.51619114 0.0136132
- DAT_T+ 0.04072031 0.08458963 414.0000 0.48138651 1.0000000
DAT_T- - DAT_T+ -0.33245197 0.10911305 414.0000 -3.04685815 0.0688942
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(TNFR2_NPX, na.rm = TRUE), Std=sd(TNFR2_NPX, na.rm = TRUE),
Max=max(TNFR2_NPX, na.rm = TRUE), Min=min(TNFR2_NPX, na.rm = TRUE))5.12. ICAM1_Diag+T
(ICAM1_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = ICAM1_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "ICAM1 (NPX)") +
scale_y_continuous(breaks = seq(-6,-1, by = 1), limits = c(-6, -1)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = ICAM1_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = ICAM1_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - ICAM1_NPX
────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 5.77599441 7 0.82514206 5.4012248 0.0000061
Age 1.49814382 1 1.49814382 9.8065679 0.0018623
sex 1.15535612 1 1.15535612 7.5627440 0.0062199
bmi 0.60163276 1 0.60163276 3.9381750 0.0478617
E4_Positive 0.02363033 1 0.02363033 0.1546797 0.6943053
Residuals 63.24654548 414 0.15276943
────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.200895776 0.10001745 414.0000 -2.00860728 1.0000000
- SCD_T- 0.046712387 0.05392559 414.0000 0.86623788 1.0000000
- SCD_T+ -0.265283012 0.08548694 414.0000 -3.10319927 0.0572791
- MCI_T- -0.116199411 0.07223935 414.0000 -1.60853355 1.0000000
- MCI_T+ -0.197279340 0.07557853 414.0000 -2.61025652 0.2625179
- DAT_T- -0.090095240 0.10772222 414.0000 -0.83636638 1.0000000
- DAT_T+ -0.297782969 0.08514204 414.0000 -3.49748469 0.0145748
CN_T+ - SCD_T- 0.247608163 0.09601750 414.0000 2.57878153 0.2872592
- SCD_T+ -0.064387236 0.11537235 414.0000 -0.55808201 1.0000000
- MCI_T- 0.084696365 0.10748575 414.0000 0.78797758 1.0000000
- MCI_T+ 0.003616436 0.10858116 414.0000 0.03330630 1.0000000
- DAT_T- 0.110800537 0.13271885 414.0000 0.83485156 1.0000000
- DAT_T+ -0.096887193 0.11456416 414.0000 -0.84570248 1.0000000
SCD_T- - SCD_T+ -0.311995399 0.07913277 414.0000 -3.94268242 0.0026486
- MCI_T- -0.162911798 0.06592165 414.0000 -2.47129432 0.3881922
- MCI_T+ -0.243991727 0.06887537 414.0000 -3.54251078 0.0123605
- DAT_T- -0.136807627 0.10199169 414.0000 -1.34136050 1.0000000
- DAT_T+ -0.344495356 0.07744717 414.0000 -4.44813360 0.0003121
SCD_T+ - MCI_T- 0.149083601 0.09192212 414.0000 1.62184692 1.0000000
- MCI_T+ 0.068003672 0.09343851 414.0000 0.72779061 1.0000000
- DAT_T- 0.175187772 0.11963712 414.0000 1.46432626 1.0000000
- DAT_T+ -0.032499957 0.09902710 414.0000 -0.32819256 1.0000000
MCI_T- - MCI_T+ -0.081079929 0.08352770 414.0000 -0.97069514 1.0000000
- DAT_T- 0.026104172 0.11222843 414.0000 0.23259856 1.0000000
- DAT_T+ -0.181583558 0.09050407 414.0000 -2.00635796 1.0000000
MCI_T+ - DAT_T- 0.107184100 0.11306067 414.0000 0.94802284 1.0000000
- DAT_T+ -0.100503629 0.09011390 414.0000 -1.11529551 1.0000000
DAT_T- - DAT_T+ -0.207687730 0.11623886 414.0000 -1.78673231 1.0000000
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(ICAM1_NPX, na.rm = TRUE), Std=sd(ICAM1_NPX, na.rm = TRUE),
Max=max(ICAM1_NPX, na.rm = TRUE), Min=min(ICAM1_NPX, na.rm = TRUE))5.13. VCAM1_Diag+T
(VCAM1_Diag_T_plot <- ggplot(DC_thesis_o,
aes(x = clinical_N_cat, y = VCAM1_NPX,
colour = clinical_N_cat, fill = clinical_N_cat)) +
geom_boxplot() +
geom_jitter(pch = 18, size = 1, alpha = 0.8, width = 0.2) +
labs(x = NULL, y = "VCAM1 (NPX)") +
scale_y_continuous(breaks = seq(-3,1, by = 1), limits = c(-3, 1)) +
scale_colour_manual(values = c("black",'black', "black", "black",
"black", "black","black", 'black')) +
scale_fill_manual(values = c("honeydew3",'bisque2', "lightblue", "darkorange3",
"lightgreen", "coral","aquamarine2", 'deeppink')) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()))
ancova(formula = VCAM1_NPX ~ clinical_N_cat +
Age +
sex +
bmi +
E4_Positive,
data = DC_thesis_o,
postHoc = VCAM1_NPX ~ clinical_N_cat,
postHocCorr = "bonf")
ANCOVA
ANCOVA - VCAM1_NPX
─────────────────────────────────────────────────────────────────────────────────────
Sum of Squares df Mean Square F p
─────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat 5.33952762 7 0.76278966 6.5941411 0.0000002
Age 2.48870078 1 2.48870078 21.5142457 0.0000047
sex 2.97344854 1 2.97344854 25.7047786 0.0000006
bmi 0.14679053 1 0.14679053 1.2689703 0.2606125
E4_Positive 0.03388809 1 0.03388809 0.2929547 0.5886244
Residuals 47.89022763 414 0.11567688
─────────────────────────────────────────────────────────────────────────────────────
POST HOC TESTS
Post Hoc Comparisons - clinical_N_cat
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
clinical_N_cat clinical_N_cat Mean Difference SE df t p-bonferroni
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
CN_T- - CN_T+ -0.224082797 0.08703237 414.0000 -2.57470631 0.2906104
- SCD_T- 0.049693970 0.04692453 414.0000 1.05901900 1.0000000
- SCD_T+ -0.287811852 0.07438833 414.0000 -3.86904564 0.0035527
- MCI_T- -0.024219452 0.06286065 414.0000 -0.38528798 1.0000000
- MCI_T+ -0.170015759 0.06576631 414.0000 -2.58514981 0.2820914
- DAT_T- 0.052503278 0.09373684 414.0000 0.56011357 1.0000000
- DAT_T+ -0.219850841 0.07408821 414.0000 -2.96742022 0.0889647
CN_T+ - SCD_T- 0.273776766 0.08355173 414.0000 3.27673361 0.0318820
- SCD_T+ -0.063729055 0.10039378 414.0000 -0.63479088 1.0000000
- MCI_T- 0.199863345 0.09353108 414.0000 2.13686555 0.9294455
- MCI_T+ 0.054067037 0.09448427 414.0000 0.57223319 1.0000000
- DAT_T- 0.276586075 0.11548821 414.0000 2.39492913 0.4778819
- DAT_T+ 0.004231955 0.09969051 414.0000 0.04245094 1.0000000
SCD_T- - SCD_T+ -0.337505821 0.06885912 414.0000 -4.90139642 0.0000383
- MCI_T- -0.073913421 0.05736317 414.0000 -1.28851712 1.0000000
- MCI_T+ -0.219709729 0.05993341 414.0000 -3.66589753 0.0077995
- DAT_T- 0.002809309 0.08875030 414.0000 0.03165407 1.0000000
- DAT_T+ -0.269544811 0.06739235 414.0000 -3.99963518 0.0021038
SCD_T+ - MCI_T- 0.263592400 0.07998804 414.0000 3.29539763 0.0298887
- MCI_T+ 0.117796093 0.08130757 414.0000 1.44877160 1.0000000
- DAT_T- 0.340315130 0.10410486 414.0000 3.26896502 0.0327474
- DAT_T+ 0.067961011 0.08617060 414.0000 0.78867981 1.0000000
MCI_T- - MCI_T+ -0.145796307 0.07268345 414.0000 -2.00590784 1.0000000
- DAT_T- 0.076722730 0.09765802 414.0000 0.78562648 1.0000000
- DAT_T+ -0.195631389 0.07875410 414.0000 -2.48407893 0.3747312
MCI_T+ - DAT_T- 0.222519037 0.09838222 414.0000 2.26178103 0.6784082
- DAT_T+ -0.049835082 0.07841458 414.0000 -0.63553334 1.0000000
DAT_T- - DAT_T+ -0.272354119 0.10114779 414.0000 -2.69263542 0.2065483
─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Note. Comparisons are based on estimated marginal meansDC_thesis_o%>%
group_by(clinical_N_cat)%>%
summarise(Median=median(VCAM1_NPX, na.rm = TRUE), Std=sd(VCAM1_NPX, na.rm = TRUE),
Max=max(VCAM1_NPX, na.rm = TRUE), Min=min(VCAM1_NPX, na.rm = TRUE))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